Document - An experience in using machine learning for short-term predictions in smart transportation systems

2017

Journal article Open Access

An experience in using machine learning for short-term predictions in smart transportation systems

Bacciu D., Carta A., Gnesi S., Semini L.

Computational Theory and Mathematics Bike-sharing systems Machine learning techniques Theoretical Computer Science Prediction Software Logic

Bike-sharing systems (BSS) are a means of smart transportation with the benefit of a positive impact on urban mobility. To improve the satisfaction of a user of a BSS, it is useful to inform her/him on the status of the stations at run time, and indeed most of the current systems provide the information in terms of number of bicycles parked in each docking stations by means of services available via web. However, when the departure station is empty, the user could also be happy to know how the situation will evolve and, in particular, if a bike is going to arrive (and vice versa when the arrival station is full). To fulfill this expectation, we envisage services able to make a prediction and infer if there is in use a bike that could be, with high probability, returned at the station where she/he is waiting. The goal of this paper is hence to analyze the feasibility of these services. To this end, we put forward the idea of using Machine Learning methodologies, proposing and comparing different solutions. (C) 2016 Elsevier Inc. All rights reserved.

Source: Journal of Logical and Algebraic Methods in Programming [online] 87 (2017): 52–66. doi:10.1016/j.jlamp.2016.11.002

Publisher: Elsevier, Amsterdam, NH.

Metrics

Back to previous page

Cite as

BibTeX entry

@article{oai:it.cnr:prodotti:384023,
	title = {An experience in using machine learning for short-term predictions in smart transportation systems},
	author = {Bacciu D. and Carta A. and Gnesi S. and Semini L.},
	publisher = {Elsevier, Amsterdam, NH.},
	doi = {10.1016/j.jlamp.2016.11.002},
	journal = {Journal of Logical and Algebraic Methods in Programming [online]},
	volume = {87},
	pages = {52–66},
	year = {2017}
}